AI News

Read the Room Before Your Model Generates (arxiv.org)

Self-Evolving Agent Harness (arxiv.org)

Cross-Market Meta-Learning for Electricity Price Forecasting (arxiv.org)

Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents (arxiv.org)

BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems (arxiv.org)

Jeva: System One Models from First Principles (arxiv.org)

Beyond the Verdict: Agentic Code Judging with Verifiable Feedback (arxiv.org)

Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis (arxiv.org)

Order-Consistent Latent Geometry for Reliable Short-Horizon Planning in World Models (arxiv.org)

Configuring RAG Systems: What Breaks, Where Originates, and How to Fix (arxiv.org)

Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry (arxiv.org)

Where Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Science (arxiv.org)

Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems (arxiv.org)

When Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark (arxiv.org)

Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection (arxiv.org)

AI Representations of Mental Health Stigma: Quantifying the Gap Between AI Estimations and Human Perceptions Across Gender Groups Using GPT-Based LLMs (arxiv.org)

Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecasting (arxiv.org)

InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design (arxiv.org)

Learning Across Temporal Graph Representation Silos (arxiv.org)

TEX-MEX: Similarity-Guided Temporal Contrastive Learning for Time Series (arxiv.org)

Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following (arxiv.org)

When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents (arxiv.org)

When Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems (arxiv.org)

OT-FlowRec: Optimal Transport-Guided Multi-Bridge Flow for Multimodal Sequential Recommendation (arxiv.org)

Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents (arxiv.org)

When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits (arxiv.org)

Plans Fade Fast: Why Context Management Is Load-Bearing for LLM Agents (arxiv.org)

Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems (arxiv.org)

HankelKANet: Lightweight Path Loss Estimation via Physics-Inspired Hankel Convolution (arxiv.org)

CktHGVAE: A Symmetric Design/State Heterogeneous Graph Variational Autoencoder for Transistor-level Analog/Mixed-signal Circuit Design and Analysis (arxiv.org)

SKG: A Law-Induced Engine from Inference to Induction (arxiv.org)

MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces (arxiv.org)

Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents (arxiv.org)

MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck (arxiv.org)

PID-Gated Continual Prompt Adaptation Under Noisy Feedback (arxiv.org)

Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment (arxiv.org)

Hardware-Assisted Multi-Stage Ransomware Detection with Adaptive Machine Learning (arxiv.org)

DiffNash: Finding Nash Equilibrium in High-Dimensional Continuous Action Spaces with Diffusion Policies (arxiv.org)

Scalable Weak-to-Strong Verifier Hardening for Agent Environments (arxiv.org)

Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models (arxiv.org)

Two-stage Residual Learning for Modelling Strength-Informed Optimisation of Thermal Systems (arxiv.org)

Comprehensive Comparisons of Reinforcement Learning Algorithms in Autonomous Driving (arxiv.org)

W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition (arxiv.org)

Train to Stitch: Topology-Preserving Regularization for Interoperable Representations (arxiv.org)

Selective Next-Location Prediction with MetaModelSelect: A Lightweight Post-Hoc Confidence Metamodel (arxiv.org)

LaCache: Robust Semantic Caching for LLM Serving (arxiv.org)

Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation (arxiv.org)

RINO: Renormalization Group Distillation with No Labels (arxiv.org)

Gen Through the Lens: Camera-Controllable Video Generation via Cross-Coordinate Conditioning Fusion (arxiv.org)

Review Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines (arxiv.org)